INDEX

Explanations

American Publishers

New Auto-Interp

Top Features by Cosine Similarity

Configuration

Prompts (Dashboard)

10,000 prompts, 128 tokens each

Dataset (Dashboard)

lmsys/lmsys-chat-1m

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

.printStackTrace

-0.11

 Hayward

-0.10

endregion

-0.10

atrix

-0.10

 Parad

-0.09

avad

-0.09

.CodeAnalysis

-0.09

 konkrÃ©t

-0.09

alls

-0.08

IST

-0.08

POSITIVE LOGITS

 erotik

0.11

ARSE

0.10

 audience

0.10

 audiences

0.10

ANNEL

0.09

 loyal

0.09

ypse

0.09

 CascadeType

0.09

PFN

0.09

 Graz

0.09

Activations Density 0.010%